Corresponds to path b in the mediation (effect of threat composite on projection)
data_bfi <- clean_data_bfi %>%
select(sub_id, bfi_number, bfi_targ_pmc, bfi_self_pmc, itt_comp_gmc,
target_condition, bfi_targ, bfi_self, bfi_stereo, bfi_stereo_pmc) %>%
unique() %>%
na.omit()
bfi_nostereo_comp <- lmer(bfi_targ_pmc ~ bfi_self_pmc*itt_comp_gmc +
(bfi_self_pmc | sub_id), data = data_bfi)
summary(bfi_nostereo_comp)
## Linear mixed model fit by REML ['lmerMod']
## Formula: bfi_targ_pmc ~ bfi_self_pmc * itt_comp_gmc + (bfi_self_pmc |
## sub_id)
## Data: data_bfi
##
## REML criterion at convergence: 23334.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.7620 -0.6103 -0.0189 0.6510 3.5515
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## sub_id (Intercept) 0.15039 0.3878
## bfi_self_pmc 0.05783 0.2405 0.64
## Residual 0.94067 0.9699
## Number of obs: 8056, groups: sub_id, 424
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) 0.010483 0.021846 0.480
## bfi_self_pmc 0.005026 0.014560 0.345
## itt_comp_gmc -0.293358 0.020406 -14.376
## bfi_self_pmc:itt_comp_gmc -0.133187 0.013539 -9.837
##
## Correlation of Fixed Effects:
## (Intr) bf_sl_ itt_c_
## bfi_slf_pmc 0.446
## itt_cmp_gmc 0.000 0.000
## bf_slf_p:__ 0.000 -0.015 0.437
tab_model(bfi_nostereo_comp)
| bfi_targ_pmc | |||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 0.01 | -0.03 – 0.05 | 0.631 |
| bfi self pmc | 0.01 | -0.02 – 0.03 | 0.730 |
| itt comp gmc | -0.29 | -0.33 – -0.25 | <0.001 |
|
bfi self pmc * itt comp gmc |
-0.13 | -0.16 – -0.11 | <0.001 |
| Random Effects | |||
| σ2 | 0.94 | ||
| τ00 sub_id | 0.15 | ||
| τ11 sub_id.bfi_self_pmc | 0.06 | ||
| ρ01 sub_id | 0.64 | ||
| ICC | 0.21 | ||
| N sub_id | 424 | ||
| Observations | 8056 | ||
| Marginal R2 / Conditional R2 | 0.105 / 0.294 | ||
threat_levels = list(itt_comp_gmc = c(-1.07, 0.0, 1.07))
simpslopes_bfi_nostereo2 <- emtrends(bfi_nostereo_comp, ~ itt_comp_gmc,
var ="bfi_self_pmc",
at = c(threat_levels))
simpslopes_bfi_nostereo2
## itt_comp_gmc bfi_self_pmc.trend SE df asymp.LCL asymp.UCL
## -1.07 0.14754 0.0207 Inf 0.1070 0.1881
## 0.00 0.00503 0.0146 Inf -0.0235 0.0336
## 1.07 -0.13748 0.0204 Inf -0.1774 -0.0975
##
## Degrees-of-freedom method: asymptotic
## Confidence level used: 0.95
test(simpslopes_bfi_nostereo2)
## itt_comp_gmc bfi_self_pmc.trend SE df z.ratio p.value
## -1.07 0.14754 0.0207 Inf 7.131 <.0001
## 0.00 0.00503 0.0146 Inf 0.345 0.7300
## 1.07 -0.13748 0.0204 Inf -6.743 <.0001
##
## Degrees-of-freedom method: asymptotic
pairs(simpslopes_bfi_nostereo2)
## contrast estimate SE df z.ratio p.value
## (-1.07) - 0 0.143 0.0145 Inf 9.837 <.0001
## (-1.07) - 1.07 0.285 0.0290 Inf 9.837 <.0001
## 0 - 1.07 0.143 0.0145 Inf 9.837 <.0001
##
## Degrees-of-freedom method: asymptotic
## P value adjustment: tukey method for comparing a family of 3 estimates
bfi_nostereo_comp_df <- effect("bfi_self_pmc:itt_comp_gmc",
xlevels = list(itt_comp_gmc = c(-1.07, 0.0, 1.07)),
mod = bfi_nostereo_comp)
bfi_nostereo_comp_df <- as.data.frame(bfi_nostereo_comp_df)
bfi_nostereo_comp_df$itt_comp_gmc <- as.factor(bfi_nostereo_comp_df$itt_comp_gmc)
ggplot(bfi_nostereo_comp_df, aes(bfi_self_pmc, fit, group = itt_comp_gmc)) +
geom_smooth(method = "lm",
size = .7,
se = FALSE,
colour = "black",
aes(linetype = itt_comp_gmc)) +
theme_minimal(base_size = 13) +
theme(legend.key.size = unit(1, "cm")) +
scale_linetype_manual("Threat composite",
breaks = c("-1.07", "0", "1.07"),
labels = c("Low",
"Average",
"High"),
values = c("solid",
"dashed",
"dotted")) +
labs(title = "Projection by target-level threat",
subtitle = "Using the BFI",
x = "BFI responses for self",
y = "BFI responses for target")
# checking normality of conditional residuals
qqnorm(residuals(bfi_nostereo_comp), main="Q-Q plot for conditional residuals")
# checking the normality of the random effects (here random intercept):
qqnorm(ranef(bfi_nostereo_comp)$sub_id$bfi_self_pmc,
main="Q-Q plot for the self random effect")
# Checking residuals for intercept
qqnorm(ranef(bfi_nostereo_comp)$sub_id$`(Intercept)`,
main="Q-Q plot for the random intercept")
plot_model(bfi_nostereo_comp, type='diag')
## [[1]]
##
## [[2]]
## [[2]]$sub_id
##
##
## [[3]]
##
## [[4]]
Adding condition to test the effect of context
bfi_nostereo <- lmer(bfi_targ_pmc ~ bfi_self_pmc*itt_comp_gmc*target_condition +
(bfi_self_pmc | sub_id), data = data_bfi)
summary(bfi_nostereo)
## Linear mixed model fit by REML ['lmerMod']
## Formula: bfi_targ_pmc ~ bfi_self_pmc * itt_comp_gmc * target_condition +
## (bfi_self_pmc | sub_id)
## Data: data_bfi
##
## REML criterion at convergence: 23271.4
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.7362 -0.6065 -0.0027 0.6459 3.5778
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## sub_id (Intercept) 0.1125 0.3354
## bfi_self_pmc 0.0520 0.2280 0.59
## Residual 0.9409 0.9700
## Number of obs: 8056, groups: sub_id, 424
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) 0.31738 0.05346 5.937
## bfi_self_pmc 0.16899 0.03842 4.398
## itt_comp_gmc -0.08692 0.04235 -2.052
## target_conditionLOSS -0.59813 0.07366 -8.120
## target_conditionWARM -0.22371 0.06553 -3.414
## bfi_self_pmc:itt_comp_gmc -0.01817 0.03037 -0.598
## bfi_self_pmc:target_conditionLOSS -0.27560 0.05325 -5.176
## bfi_self_pmc:target_conditionWARM -0.13766 0.04715 -2.919
## itt_comp_gmc:target_conditionLOSS -0.15326 0.06653 -2.304
## itt_comp_gmc:target_conditionWARM -0.11810 0.05935 -1.990
## bfi_self_pmc:itt_comp_gmc:target_conditionLOSS -0.08013 0.04768 -1.681
## bfi_self_pmc:itt_comp_gmc:target_conditionWARM -0.10539 0.04264 -2.472
##
## Correlation of Fixed Effects:
## (Intr) bf_sl_ itt_c_ t_LOSS t_WARM bf__:__ b__:_L b__:_W i__:_L
## bfi_slf_pmc 0.402
## itt_cmp_gmc 0.787 0.316
## trgt_cnLOSS -0.726 -0.291 -0.571
## trgt_cnWARM -0.816 -0.328 -0.642 0.592
## bf_slf_p:__ 0.317 0.788 0.391 -0.230 -0.259
## bf_s_:_LOSS -0.290 -0.722 -0.228 0.386 0.236 -0.569
## bf_s_:_WARM -0.327 -0.815 -0.258 0.237 0.405 -0.642 0.588
## itt__:_LOSS -0.501 -0.201 -0.637 -0.011 0.409 -0.249 0.009 0.164
## itt__:_WARM -0.561 -0.226 -0.714 0.407 0.272 -0.279 0.163 0.103 0.454
## b__:__:_LOS -0.202 -0.502 -0.249 0.009 0.165 -0.637 -0.022 0.409 0.374
## b__:__:_WAR -0.226 -0.561 -0.279 0.164 0.103 -0.712 0.405 0.261 0.177
## i__:_W b__:__:_L
## bfi_slf_pmc
## itt_cmp_gmc
## trgt_cnLOSS
## trgt_cnWARM
## bf_slf_p:__
## bf_s_:_LOSS
## bf_s_:_WARM
## itt__:_LOSS
## itt__:_WARM
## b__:__:_LOS 0.178
## b__:__:_WAR 0.397 0.454
tab_model(bfi_nostereo)
| bfi_targ_pmc | |||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 0.32 | 0.21 – 0.42 | <0.001 |
| bfi self pmc | 0.17 | 0.09 – 0.24 | <0.001 |
| itt comp gmc | -0.09 | -0.17 – -0.00 | 0.040 |
| target condition [LOSS] | -0.60 | -0.74 – -0.45 | <0.001 |
| target condition [WARM] | -0.22 | -0.35 – -0.10 | 0.001 |
|
bfi self pmc * itt comp gmc |
-0.02 | -0.08 – 0.04 | 0.550 |
|
bfi self pmc * target condition [LOSS] |
-0.28 | -0.38 – -0.17 | <0.001 |
|
bfi self pmc * target condition [WARM] |
-0.14 | -0.23 – -0.05 | 0.004 |
|
itt comp gmc * target condition [LOSS] |
-0.15 | -0.28 – -0.02 | 0.021 |
|
itt comp gmc * target condition [WARM] |
-0.12 | -0.23 – -0.00 | 0.047 |
|
(bfi self pmc * itt comp gmc) * target condition [LOSS] |
-0.08 | -0.17 – 0.01 | 0.093 |
|
(bfi self pmc * itt comp gmc) * target condition [WARM] |
-0.11 | -0.19 – -0.02 | 0.013 |
| Random Effects | |||
| σ2 | 0.94 | ||
| τ00 sub_id | 0.11 | ||
| τ11 sub_id.bfi_self_pmc | 0.05 | ||
| ρ01 sub_id | 0.59 | ||
| ICC | 0.18 | ||
| N sub_id | 424 | ||
| Observations | 8056 | ||
| Marginal R2 / Conditional R2 | 0.142 / 0.295 | ||
targ_levels <-list(target_condition = c("CONTROL", "LOSS", "WARM"))
simpslopes_bfi_nostereo1 <- emtrends(bfi_nostereo, ~ itt_comp_gmc*target_condition,
var ="bfi_self_pmc",
at = c(targ_levels, threat_levels))
simpslopes_bfi_nostereo1
## itt_comp_gmc target_condition bfi_self_pmc.trend SE df asymp.LCL
## -1.07 CONTROL 0.18843 0.0238 Inf 0.1419
## 0.00 CONTROL 0.16899 0.0384 Inf 0.0937
## 1.07 CONTROL 0.14955 0.0671 Inf 0.0181
## -1.07 LOSS -0.00143 0.0707 Inf -0.1399
## 0.00 LOSS -0.10661 0.0369 Inf -0.1789
## 1.07 LOSS -0.21180 0.0286 Inf -0.2679
## -1.07 WARM 0.16354 0.0511 Inf 0.0633
## 0.00 WARM 0.03133 0.0273 Inf -0.0222
## 1.07 WARM -0.10087 0.0305 Inf -0.1607
## asymp.UCL
## 0.2350
## 0.2443
## 0.2810
## 0.1371
## -0.0344
## -0.1557
## 0.2638
## 0.0849
## -0.0411
##
## Degrees-of-freedom method: asymptotic
## Confidence level used: 0.95
test(simpslopes_bfi_nostereo1)
## itt_comp_gmc target_condition bfi_self_pmc.trend SE df z.ratio p.value
## -1.07 CONTROL 0.18843 0.0238 Inf 7.931 <.0001
## 0.00 CONTROL 0.16899 0.0384 Inf 4.398 <.0001
## 1.07 CONTROL 0.14955 0.0671 Inf 2.230 0.0258
## -1.07 LOSS -0.00143 0.0707 Inf -0.020 0.9839
## 0.00 LOSS -0.10661 0.0369 Inf -2.892 0.0038
## 1.07 LOSS -0.21180 0.0286 Inf -7.401 <.0001
## -1.07 WARM 0.16354 0.0511 Inf 3.198 0.0014
## 0.00 WARM 0.03133 0.0273 Inf 1.146 0.2517
## 1.07 WARM -0.10087 0.0305 Inf -3.306 0.0009
##
## Degrees-of-freedom method: asymptotic
pairs(simpslopes_bfi_nostereo1)
## contrast estimate SE df z.ratio p.value
## (-1.07 CONTROL) - 0 CONTROL 0.01944 0.0325 Inf 0.598 0.9996
## (-1.07 CONTROL) - 1.07 CONTROL 0.03888 0.0650 Inf 0.598 0.9996
## (-1.07 CONTROL) - (-1.07 LOSS) 0.18986 0.0745 Inf 2.547 0.2096
## (-1.07 CONTROL) - 0 LOSS 0.29504 0.0439 Inf 6.727 <.0001
## (-1.07 CONTROL) - 1.07 LOSS 0.40023 0.0372 Inf 10.761 <.0001
## (-1.07 CONTROL) - (-1.07 WARM) 0.02489 0.0564 Inf 0.441 1.0000
## (-1.07 CONTROL) - 0 WARM 0.15710 0.0362 Inf 4.337 0.0005
## (-1.07 CONTROL) - 1.07 WARM 0.28931 0.0387 Inf 7.482 <.0001
## 0 CONTROL - 1.07 CONTROL 0.01944 0.0325 Inf 0.598 0.9996
## 0 CONTROL - (-1.07 LOSS) 0.17042 0.0804 Inf 2.119 0.4602
## 0 CONTROL - 0 LOSS 0.27560 0.0532 Inf 5.176 <.0001
## 0 CONTROL - 1.07 LOSS 0.38079 0.0479 Inf 7.949 <.0001
## 0 CONTROL - (-1.07 WARM) 0.00545 0.0640 Inf 0.085 1.0000
## 0 CONTROL - 0 WARM 0.13766 0.0472 Inf 2.919 0.0841
## 0 CONTROL - 1.07 WARM 0.26986 0.0491 Inf 5.501 <.0001
## 1.07 CONTROL - (-1.07 LOSS) 0.15098 0.0974 Inf 1.550 0.8318
## 1.07 CONTROL - 0 LOSS 0.25616 0.0765 Inf 3.347 0.0232
## 1.07 CONTROL - 1.07 LOSS 0.36134 0.0729 Inf 4.955 <.0001
## 1.07 CONTROL - (-1.07 WARM) -0.01400 0.0844 Inf -0.166 1.0000
## 1.07 CONTROL - 0 WARM 0.11821 0.0724 Inf 1.632 0.7873
## 1.07 CONTROL - 1.07 WARM 0.25042 0.0737 Inf 3.398 0.0195
## (-1.07 LOSS) - 0 LOSS 0.10518 0.0393 Inf 2.675 0.1568
## (-1.07 LOSS) - 1.07 LOSS 0.21037 0.0787 Inf 2.675 0.1568
## (-1.07 LOSS) - (-1.07 WARM) -0.16497 0.0872 Inf -1.891 0.6199
## (-1.07 LOSS) - 0 WARM -0.03276 0.0758 Inf -0.432 1.0000
## (-1.07 LOSS) - 1.07 WARM 0.09945 0.0770 Inf 1.292 0.9340
## 0 LOSS - 1.07 LOSS 0.10518 0.0393 Inf 2.675 0.1568
## 0 LOSS - (-1.07 WARM) -0.27015 0.0630 Inf -4.285 0.0006
## 0 LOSS - 0 WARM -0.13795 0.0459 Inf -3.006 0.0661
## 0 LOSS - 1.07 WARM -0.00574 0.0479 Inf -0.120 1.0000
## 1.07 LOSS - (-1.07 WARM) -0.37534 0.0586 Inf -6.404 <.0001
## 1.07 LOSS - 0 WARM -0.24313 0.0396 Inf -6.143 <.0001
## 1.07 LOSS - 1.07 WARM -0.11092 0.0418 Inf -2.652 0.1655
## (-1.07 WARM) - 0 WARM 0.13221 0.0320 Inf 4.128 0.0012
## (-1.07 WARM) - 1.07 WARM 0.26442 0.0641 Inf 4.128 0.0012
## 0 WARM - 1.07 WARM 0.13221 0.0320 Inf 4.128 0.0012
##
## Degrees-of-freedom method: asymptotic
## P value adjustment: tukey method for comparing a family of 9 estimates
bfi_no_stereo_df <- effect("bfi_self_pmc:itt_comp_gmc:target_condition",
xlevels = list(itt_comp_gmc = c(-1.07, 0.0, 1.07),
target_condition = c("CONTROL",
"WARM",
"LOSS")),
mod = bfi_nostereo)
bfi_no_stereo_df <- as.data.frame(bfi_no_stereo_df)
bfi_no_stereo_df$itt_comp_gmc <- as.factor(bfi_no_stereo_df$itt_comp_gmc)
bfi_no_stereo_df$target_condition <- as.factor(bfi_no_stereo_df$target_condition)
bfi_no_stereo_df %<>%
mutate(target_condition = forcats::fct_relevel(target_condition, c("CONTROL", "WARM", "LOSS")))
target_labels <- c("CONTROL" = "Control",
"WARM" = "Warm",
"LOSS" = "Loss")
ggplot(bfi_no_stereo_df, aes(bfi_self_pmc, fit, group = itt_comp_gmc)) +
geom_smooth(method = "lm",
size = .7,
se = FALSE,
colour = "black",
aes(linetype = itt_comp_gmc)) +
theme_minimal(base_size = 13) +
theme(legend.key.size = unit(1, "cm")) +
facet_wrap(~target_condition,
labeller = labeller(target_condition = target_labels)) +
scale_linetype_manual("Threat composite",
breaks = c("-1.07", "0", "1.07"),
labels = c("Low",
"Average",
"High"),
values = c("solid",
"dashed",
"dotted")) +
labs(title = "Projection by target-level threat and target condition",
subtitle = "Using the BFI",
x = "BFI responses for self",
y = "BFI responses for target") +
expand_limits(x=c(-2,2), y=c(-2, 2))
plot_data_int1 <- data_bfi %>%
select(sub_id, bfi_number, bfi_self_pmc, bfi_targ_pmc, itt_comp_gmc, target_condition)
plot_data_int1$itt_comp_gmc[data_bfi$itt_comp_gmc < -1.07] <- "Low"
plot_data_int1$itt_comp_gmc[data_bfi$itt_comp_gmc > -1.07 & data_bfi$itt_comp_gmc < 1.07] <- "Ave"
plot_data_int1$itt_comp_gmc[data_bfi$itt_comp_gmc > 1.07] <- "High"
# group_by(bfi_self_pmc, itt_comp_gmc, target_condition) %>%
# mutate(mean = mean(bfi_targ_pmc),
# sd = sd(bfi_targ_pmc))
ggplot(plot_data_int1, aes(bfi_self_pmc, bfi_targ_pmc, group = itt_comp_gmc)) +
geom_smooth(method = "lm",
size = .7,
colour = "black",
aes(linetype = itt_comp_gmc)) +
theme_minimal(base_size = 13) +
theme(legend.key.size = unit(1, "cm")) +
expand_limits(x=c(-2,2), y=c(-2, 2)) +
facet_wrap(~target_condition,
labeller = labeller(target_condition = target_labels))
# checking normality of conditional residuals
qqnorm(residuals(bfi_nostereo), main="Q-Q plot for conditional residuals")
# checking the normality of the random effects (here random intercept):
qqnorm(ranef(bfi_nostereo)$sub_id$bfi_self_pmc,
main="Q-Q plot for the self random effect")
# Checking residuals for intercept
qqnorm(ranef(bfi_nostereo)$sub_id$`(Intercept)`,
main="Q-Q plot for the random intercept")
plot_model(bfi_nostereo, type='diag')
## [[1]]
##
## [[2]]
## [[2]]$sub_id
##
##
## [[3]]
##
## [[4]]
More normal, but a little tail
bfi_stereo_comp <- lmer(bfi_targ_pmc ~ bfi_self_pmc*itt_comp_gmc*bfi_stereo_pmc +
(bfi_self_pmc + bfi_stereo_pmc | sub_id), data = data_bfi)
summary(bfi_stereo_comp)
## Linear mixed model fit by REML ['lmerMod']
## Formula: bfi_targ_pmc ~ bfi_self_pmc * itt_comp_gmc * bfi_stereo_pmc +
## (bfi_self_pmc + bfi_stereo_pmc | sub_id)
## Data: data_bfi
##
## REML criterion at convergence: 21421.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.2701 -0.5006 -0.0365 0.6200 4.2064
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## sub_id (Intercept) 0.12671 0.3560
## bfi_self_pmc 0.03947 0.1987 0.46
## bfi_stereo_pmc 0.06654 0.2580 -0.69 -0.07
## Residual 0.70284 0.8384
## Number of obs: 8056, groups: sub_id, 424
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) 0.020974 0.020143 1.041
## bfi_self_pmc 0.067192 0.012663 5.306
## itt_comp_gmc -0.258769 0.018832 -13.741
## bfi_stereo_pmc 0.224519 0.015642 14.354
## bfi_self_pmc:itt_comp_gmc -0.072592 0.011798 -6.153
## bfi_self_pmc:bfi_stereo_pmc -0.017398 0.006252 -2.783
## itt_comp_gmc:bfi_stereo_pmc 0.190791 0.014562 13.102
## bfi_self_pmc:itt_comp_gmc:bfi_stereo_pmc -0.005255 0.005662 -0.928
##
## Correlation of Fixed Effects:
## (Intr) bf_sl_ itt_c_ bf_st_ bf_slf_pmc:t__ bf_slf_pmc:b__ i__:__
## bfi_slf_pmc 0.293
## itt_cmp_gmc -0.001 0.008
## bfi_str_pmc -0.480 0.052 0.026
## bf_slf_pmc:t__ 0.008 -0.026 0.287 -0.003
## bf_slf_pmc:b__ 0.140 -0.084 -0.009 0.073 0.046
## itt_cmp_:__ 0.026 -0.004 -0.481 -0.060 0.052 -0.001
## bf_s_:__:__ -0.010 0.046 0.142 -0.004 -0.079 -0.180 0.057
tab_model(bfi_stereo_comp)
| bfi_targ_pmc | |||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 0.02 | -0.02 – 0.06 | 0.298 |
| bfi self pmc | 0.07 | 0.04 – 0.09 | <0.001 |
| itt comp gmc | -0.26 | -0.30 – -0.22 | <0.001 |
| bfi stereo pmc | 0.22 | 0.19 – 0.26 | <0.001 |
|
bfi self pmc * itt comp gmc |
-0.07 | -0.10 – -0.05 | <0.001 |
|
bfi self pmc * bfi stereo pmc |
-0.02 | -0.03 – -0.01 | 0.005 |
|
itt comp gmc * bfi stereo pmc |
0.19 | 0.16 – 0.22 | <0.001 |
|
(bfi self pmc * itt comp gmc) * bfi stereo pmc |
-0.01 | -0.02 – 0.01 | 0.353 |
| Random Effects | |||
| σ2 | 0.70 | ||
| τ00 sub_id | 0.13 | ||
| τ11 sub_id.bfi_self_pmc | 0.04 | ||
| τ11 sub_id.bfi_stereo_pmc | 0.07 | ||
| ρ01 | 0.46 | ||
| -0.69 | |||
| ICC | 0.31 | ||
| N sub_id | 424 | ||
| Observations | 8056 | ||
| Marginal R2 / Conditional R2 | 0.219 / 0.458 | ||
simpslopes_bfi_stereo2 <- emtrends(bfi_stereo_comp, ~ itt_comp_gmc,
var ="bfi_self_pmc",
at = c(threat_levels))
simpslopes_bfi_stereo2
## itt_comp_gmc bfi_self_pmc.trend SE df asymp.LCL asymp.UCL
## -1.07 0.14512 0.0181 Inf 0.1096 0.1807
## 0.00 0.06757 0.0127 Inf 0.0427 0.0924
## 1.07 -0.00999 0.0177 Inf -0.0446 0.0246
##
## Degrees-of-freedom method: asymptotic
## Confidence level used: 0.95
test(simpslopes_bfi_stereo2)
## itt_comp_gmc bfi_self_pmc.trend SE df z.ratio p.value
## -1.07 0.14512 0.0181 Inf 8.002 <.0001
## 0.00 0.06757 0.0127 Inf 5.331 <.0001
## 1.07 -0.00999 0.0177 Inf -0.566 0.5717
##
## Degrees-of-freedom method: asymptotic
pairs(simpslopes_bfi_stereo2)
## contrast estimate SE df z.ratio p.value
## (-1.07) - 0 0.0776 0.0126 Inf 6.138 <.0001
## (-1.07) - 1.07 0.1551 0.0253 Inf 6.138 <.0001
## 0 - 1.07 0.0776 0.0126 Inf 6.138 <.0001
##
## Degrees-of-freedom method: asymptotic
## P value adjustment: tukey method for comparing a family of 3 estimates
bfi_stereo_comp_df <- effect("bfi_self_pmc:itt_comp_gmc",
xlevels = list(itt_comp_gmc = c(-1.07, 0.0, 1.07)),
mod = bfi_stereo_comp)
bfi_stereo_comp_df <- as.data.frame(bfi_stereo_comp_df)
bfi_stereo_comp_df$itt_comp_gmc <- as.factor(bfi_stereo_comp_df$itt_comp_gmc)
ggplot(bfi_stereo_comp_df, aes(bfi_self_pmc, fit, group = itt_comp_gmc)) +
geom_smooth(method = "lm",
size = .7,
se = FALSE,
colour = "black",
aes(linetype = itt_comp_gmc)) +
theme_minimal(base_size = 13) +
theme(legend.key.size = unit(1, "cm")) +
scale_linetype_manual("Threat composite",
breaks = c("-1.07", "0", "1.07"),
labels = c("Low",
"Average",
"High"),
values = c("solid",
"dashed",
"dotted")) +
labs(title = "Residual projection by target-level threat",
subtitle = "Using the BFI; After accounting for stereotyping",
x = "BFI responses for self",
y = "BFI responses for target")
# checking normality of conditional residuals
qqnorm(residuals(bfi_stereo_comp), main="Q-Q plot for conditional residuals")
# checking the normality of the random effects (here random intercept):
qqnorm(ranef(bfi_stereo_comp)$sub_id$bfi_self_pmc,
main="Q-Q plot for the self random effect")
qqnorm(ranef(bfi_stereo_comp)$sub_id$bfi_stereo_pmc,
main="Q-Q plot for the stereotyping random effect")
# Checking residuals for intercept
qqnorm(ranef(bfi_stereo_comp)$sub_id$`(Intercept)`,
main="Q-Q plot for the random intercept")
plot_model(bfi_stereo_comp, type='diag')
## [[1]]
##
## [[2]]
## [[2]]$sub_id
##
##
## [[3]]
##
## [[4]]
Also seems to have slight tails, basically when stereotyping is added to the model
bfi_stereo <- lmer(bfi_targ_pmc ~ bfi_self_pmc*itt_comp_gmc*target_condition*bfi_stereo_pmc +
(bfi_self_pmc + bfi_stereo_pmc | sub_id), data = data_bfi)
summary(bfi_stereo)
## Linear mixed model fit by REML ['lmerMod']
## Formula: bfi_targ_pmc ~ bfi_self_pmc * itt_comp_gmc * target_condition *
## bfi_stereo_pmc + (bfi_self_pmc + bfi_stereo_pmc | sub_id)
## Data: data_bfi
##
## REML criterion at convergence: 21350
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.2639 -0.5079 -0.0245 0.6133 4.1841
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## sub_id (Intercept) 0.08848 0.2975
## bfi_self_pmc 0.03764 0.1940 0.43
## bfi_stereo_pmc 0.04944 0.2224 -0.56 0.03
## Residual 0.70259 0.8382
## Number of obs: 8056, groups: sub_id, 424
##
## Fixed effects:
## Estimate
## (Intercept) 0.287634
## bfi_self_pmc 0.163365
## itt_comp_gmc -0.099815
## target_conditionLOSS -0.617582
## target_conditionWARM -0.188058
## bfi_stereo_pmc 0.007728
## bfi_self_pmc:itt_comp_gmc 0.002811
## bfi_self_pmc:target_conditionLOSS -0.147419
## bfi_self_pmc:target_conditionWARM -0.065816
## itt_comp_gmc:target_conditionLOSS -0.038304
## itt_comp_gmc:target_conditionWARM -0.053453
## bfi_self_pmc:bfi_stereo_pmc -0.035752
## itt_comp_gmc:bfi_stereo_pmc 0.062868
## target_conditionLOSS:bfi_stereo_pmc 0.451530
## target_conditionWARM:bfi_stereo_pmc 0.204024
## bfi_self_pmc:itt_comp_gmc:target_conditionLOSS -0.067582
## bfi_self_pmc:itt_comp_gmc:target_conditionWARM -0.086188
## bfi_self_pmc:itt_comp_gmc:bfi_stereo_pmc -0.025348
## bfi_self_pmc:target_conditionLOSS:bfi_stereo_pmc -0.014208
## bfi_self_pmc:target_conditionWARM:bfi_stereo_pmc 0.021346
## itt_comp_gmc:target_conditionLOSS:bfi_stereo_pmc 0.029386
## itt_comp_gmc:target_conditionWARM:bfi_stereo_pmc 0.054390
## bfi_self_pmc:itt_comp_gmc:target_conditionLOSS:bfi_stereo_pmc 0.051846
## bfi_self_pmc:itt_comp_gmc:target_conditionWARM:bfi_stereo_pmc 0.022880
## Std. Error
## (Intercept) 0.047980
## bfi_self_pmc 0.033696
## itt_comp_gmc 0.038063
## target_conditionLOSS 0.066315
## target_conditionWARM 0.058848
## bfi_stereo_pmc 0.037254
## bfi_self_pmc:itt_comp_gmc 0.026747
## bfi_self_pmc:target_conditionLOSS 0.047254
## bfi_self_pmc:target_conditionWARM 0.041495
## itt_comp_gmc:target_conditionLOSS 0.059942
## itt_comp_gmc:target_conditionWARM 0.053410
## bfi_self_pmc:bfi_stereo_pmc 0.015259
## itt_comp_gmc:bfi_stereo_pmc 0.029961
## target_conditionLOSS:bfi_stereo_pmc 0.053965
## target_conditionWARM:bfi_stereo_pmc 0.046664
## bfi_self_pmc:itt_comp_gmc:target_conditionLOSS 0.042426
## bfi_self_pmc:itt_comp_gmc:target_conditionWARM 0.037642
## bfi_self_pmc:itt_comp_gmc:bfi_stereo_pmc 0.012337
## bfi_self_pmc:target_conditionLOSS:bfi_stereo_pmc 0.023531
## bfi_self_pmc:target_conditionWARM:bfi_stereo_pmc 0.020008
## itt_comp_gmc:target_conditionLOSS:bfi_stereo_pmc 0.048745
## itt_comp_gmc:target_conditionWARM:bfi_stereo_pmc 0.042413
## bfi_self_pmc:itt_comp_gmc:target_conditionLOSS:bfi_stereo_pmc 0.020462
## bfi_self_pmc:itt_comp_gmc:target_conditionWARM:bfi_stereo_pmc 0.018110
## t value
## (Intercept) 5.995
## bfi_self_pmc 4.848
## itt_comp_gmc -2.622
## target_conditionLOSS -9.313
## target_conditionWARM -3.196
## bfi_stereo_pmc 0.207
## bfi_self_pmc:itt_comp_gmc 0.105
## bfi_self_pmc:target_conditionLOSS -3.120
## bfi_self_pmc:target_conditionWARM -1.586
## itt_comp_gmc:target_conditionLOSS -0.639
## itt_comp_gmc:target_conditionWARM -1.001
## bfi_self_pmc:bfi_stereo_pmc -2.343
## itt_comp_gmc:bfi_stereo_pmc 2.098
## target_conditionLOSS:bfi_stereo_pmc 8.367
## target_conditionWARM:bfi_stereo_pmc 4.372
## bfi_self_pmc:itt_comp_gmc:target_conditionLOSS -1.593
## bfi_self_pmc:itt_comp_gmc:target_conditionWARM -2.290
## bfi_self_pmc:itt_comp_gmc:bfi_stereo_pmc -2.055
## bfi_self_pmc:target_conditionLOSS:bfi_stereo_pmc -0.604
## bfi_self_pmc:target_conditionWARM:bfi_stereo_pmc 1.067
## itt_comp_gmc:target_conditionLOSS:bfi_stereo_pmc 0.603
## itt_comp_gmc:target_conditionWARM:bfi_stereo_pmc 1.282
## bfi_self_pmc:itt_comp_gmc:target_conditionLOSS:bfi_stereo_pmc 2.534
## bfi_self_pmc:itt_comp_gmc:target_conditionWARM:bfi_stereo_pmc 1.263
tab_model(bfi_stereo)
| bfi_targ_pmc | |||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 0.29 | 0.19 – 0.38 | <0.001 |
| bfi self pmc | 0.16 | 0.10 – 0.23 | <0.001 |
| itt comp gmc | -0.10 | -0.17 – -0.03 | 0.009 |
| target condition [LOSS] | -0.62 | -0.75 – -0.49 | <0.001 |
| target condition [WARM] | -0.19 | -0.30 – -0.07 | 0.001 |
| bfi stereo pmc | 0.01 | -0.07 – 0.08 | 0.836 |
|
bfi self pmc * itt comp gmc |
0.00 | -0.05 – 0.06 | 0.916 |
|
bfi self pmc * target condition [LOSS] |
-0.15 | -0.24 – -0.05 | 0.002 |
|
bfi self pmc * target condition [WARM] |
-0.07 | -0.15 – 0.02 | 0.113 |
|
itt comp gmc * target condition [LOSS] |
-0.04 | -0.16 – 0.08 | 0.523 |
|
itt comp gmc * target condition [WARM] |
-0.05 | -0.16 – 0.05 | 0.317 |
|
bfi self pmc * bfi stereo pmc |
-0.04 | -0.07 – -0.01 | 0.019 |
|
itt comp gmc * bfi stereo pmc |
0.06 | 0.00 – 0.12 | 0.036 |
|
target condition [LOSS] * bfi stereo pmc |
0.45 | 0.35 – 0.56 | <0.001 |
|
target condition [WARM] * bfi stereo pmc |
0.20 | 0.11 – 0.30 | <0.001 |
|
(bfi self pmc * itt comp gmc) * target condition [LOSS] |
-0.07 | -0.15 – 0.02 | 0.111 |
|
(bfi self pmc * itt comp gmc) * target condition [WARM] |
-0.09 | -0.16 – -0.01 | 0.022 |
|
(bfi self pmc * itt comp gmc) * bfi stereo pmc |
-0.03 | -0.05 – -0.00 | 0.040 |
|
(bfi self pmc * target condition [LOSS]) * bfi stereo pmc |
-0.01 | -0.06 – 0.03 | 0.546 |
|
(bfi self pmc * target condition [WARM]) * bfi stereo pmc |
0.02 | -0.02 – 0.06 | 0.286 |
|
(itt comp gmc * target condition [LOSS]) * bfi stereo pmc |
0.03 | -0.07 – 0.12 | 0.547 |
|
(itt comp gmc * target condition [WARM]) * bfi stereo pmc |
0.05 | -0.03 – 0.14 | 0.200 |
|
(bfi self pmc * itt comp gmc * target condition [LOSS]) * bfi stereo pmc |
0.05 | 0.01 – 0.09 | 0.011 |
|
(bfi self pmc * itt comp gmc * target condition [WARM]) * bfi stereo pmc |
0.02 | -0.01 – 0.06 | 0.206 |
| Random Effects | |||
| σ2 | 0.70 | ||
| τ00 sub_id | 0.09 | ||
| τ11 sub_id.bfi_self_pmc | 0.04 | ||
| τ11 sub_id.bfi_stereo_pmc | 0.05 | ||
| ρ01 | 0.43 | ||
| -0.56 | |||
| ICC | 0.25 | ||
| N sub_id | 424 | ||
| Observations | 8056 | ||
| Marginal R2 / Conditional R2 | 0.276 / 0.457 | ||
simpslopes_bfi_stereo1 <- emtrends(bfi_stereo, ~ itt_comp_gmc*target_condition,
var ="bfi_self_pmc",
at = c(targ_levels, threat_levels))
simpslopes_bfi_stereo1
## itt_comp_gmc target_condition bfi_self_pmc.trend SE df asymp.LCL
## -1.07 CONTROL 0.1605 0.0212 Inf 0.1190
## 0.00 CONTROL 0.1641 0.0337 Inf 0.0981
## 1.07 CONTROL 0.1677 0.0589 Inf 0.0523
## -1.07 LOSS 0.0869 0.0637 Inf -0.0380
## 0.00 LOSS 0.0170 0.0332 Inf -0.0481
## 1.07 LOSS -0.0529 0.0252 Inf -0.1023
## -1.07 WARM 0.1870 0.0453 Inf 0.0982
## 0.00 WARM 0.0979 0.0242 Inf 0.0503
## 1.07 WARM 0.0087 0.0270 Inf -0.0443
## asymp.UCL
## 0.20205
## 0.23022
## 0.28311
## 0.21183
## 0.08210
## -0.00344
## 0.27587
## 0.14538
## 0.06167
##
## Degrees-of-freedom method: asymptotic
## Confidence level used: 0.95
test(simpslopes_bfi_stereo1)
## itt_comp_gmc target_condition bfi_self_pmc.trend SE df z.ratio p.value
## -1.07 CONTROL 0.1605 0.0212 Inf 7.582 <.0001
## 0.00 CONTROL 0.1641 0.0337 Inf 4.868 <.0001
## 1.07 CONTROL 0.1677 0.0589 Inf 2.849 0.0044
## -1.07 LOSS 0.0869 0.0637 Inf 1.364 0.1725
## 0.00 LOSS 0.0170 0.0332 Inf 0.513 0.6082
## 1.07 LOSS -0.0529 0.0252 Inf -2.096 0.0361
## -1.07 WARM 0.1870 0.0453 Inf 4.125 <.0001
## 0.00 WARM 0.0979 0.0242 Inf 4.036 0.0001
## 1.07 WARM 0.0087 0.0270 Inf 0.322 0.7474
##
## Degrees-of-freedom method: asymptotic
pairs(simpslopes_bfi_stereo1)
## contrast estimate SE df z.ratio p.value
## (-1.07 CONTROL) - 0 CONTROL -0.00359 0.0286 Inf -0.125 1.0000
## (-1.07 CONTROL) - 1.07 CONTROL -0.00718 0.0573 Inf -0.125 1.0000
## (-1.07 CONTROL) - (-1.07 LOSS) 0.07361 0.0672 Inf 1.096 0.9750
## (-1.07 CONTROL) - 0 LOSS 0.14352 0.0394 Inf 3.644 0.0082
## (-1.07 CONTROL) - 1.07 LOSS 0.21344 0.0329 Inf 6.480 <.0001
## (-1.07 CONTROL) - (-1.07 WARM) -0.02647 0.0500 Inf -0.529 0.9998
## (-1.07 CONTROL) - 0 WARM 0.06268 0.0322 Inf 1.947 0.5806
## (-1.07 CONTROL) - 1.07 WARM 0.15184 0.0343 Inf 4.423 0.0003
## 0 CONTROL - 1.07 CONTROL -0.00359 0.0286 Inf -0.125 1.0000
## 0 CONTROL - (-1.07 LOSS) 0.07720 0.0721 Inf 1.071 0.9784
## 0 CONTROL - 0 LOSS 0.14711 0.0473 Inf 3.109 0.0490
## 0 CONTROL - 1.07 LOSS 0.21703 0.0421 Inf 5.154 <.0001
## 0 CONTROL - (-1.07 WARM) -0.02288 0.0565 Inf -0.405 1.0000
## 0 CONTROL - 0 WARM 0.06628 0.0415 Inf 1.596 0.8075
## 0 CONTROL - 1.07 WARM 0.15543 0.0432 Inf 3.597 0.0098
## 1.07 CONTROL - (-1.07 LOSS) 0.08079 0.0868 Inf 0.931 0.9912
## 1.07 CONTROL - 0 LOSS 0.15070 0.0676 Inf 2.230 0.3861
## 1.07 CONTROL - 1.07 LOSS 0.22062 0.0640 Inf 3.445 0.0167
## 1.07 CONTROL - (-1.07 WARM) -0.01929 0.0743 Inf -0.260 1.0000
## 1.07 CONTROL - 0 WARM 0.06987 0.0637 Inf 1.097 0.9748
## 1.07 CONTROL - 1.07 WARM 0.15902 0.0648 Inf 2.455 0.2543
## (-1.07 LOSS) - 0 LOSS 0.06992 0.0353 Inf 1.981 0.5570
## (-1.07 LOSS) - 1.07 LOSS 0.13983 0.0706 Inf 1.981 0.5570
## (-1.07 LOSS) - (-1.07 WARM) -0.10008 0.0782 Inf -1.280 0.9374
## (-1.07 LOSS) - 0 WARM -0.01092 0.0682 Inf -0.160 1.0000
## (-1.07 LOSS) - 1.07 WARM 0.07823 0.0692 Inf 1.130 0.9698
## 0 LOSS - 1.07 LOSS 0.06992 0.0353 Inf 1.981 0.5570
## 0 LOSS - (-1.07 WARM) -0.16999 0.0562 Inf -3.025 0.0625
## 0 LOSS - 0 WARM -0.08084 0.0411 Inf -1.966 0.5673
## 0 LOSS - 1.07 WARM 0.00832 0.0428 Inf 0.194 1.0000
## 1.07 LOSS - (-1.07 WARM) -0.23991 0.0519 Inf -4.624 0.0001
## 1.07 LOSS - 0 WARM -0.15075 0.0350 Inf -4.308 0.0006
## 1.07 LOSS - 1.07 WARM -0.06160 0.0370 Inf -1.666 0.7674
## (-1.07 WARM) - 0 WARM 0.08916 0.0284 Inf 3.143 0.0442
## (-1.07 WARM) - 1.07 WARM 0.17831 0.0567 Inf 3.143 0.0442
## 0 WARM - 1.07 WARM 0.08916 0.0284 Inf 3.143 0.0442
##
## Degrees-of-freedom method: asymptotic
## P value adjustment: tukey method for comparing a family of 9 estimates
With residual counter-projection, people do not project nor counter-project when they report higher than average threat. Otherwise, people project normally. Though slightly different from predicted, this demonstrates that threat does reduce projection after accounting for stereotyping with those who perceive high threat, but not others. However, there is not a residual effect of counter-projection with the BFI - which I believe is consistent with PSPB.
Is this consistent with PSPB?
bfi_stereo_df <- effect("bfi_self_pmc:itt_comp_gmc:target_condition",
xlevels = list(itt_comp_gmc = c(-1.07, 0.0, 1.07),
target_condition = c("CONTROL",
"WARM",
"LOSS")),
mod = bfi_stereo)
bfi_stereo_df <- as.data.frame(bfi_stereo_df)
bfi_stereo_df$itt_comp_gmc <- as.factor(bfi_stereo_df$itt_comp_gmc)
bfi_stereo_df$target_condition <- as.factor(bfi_stereo_df$target_condition)
bfi_stereo_df %<>%
mutate(target_condition = forcats::fct_relevel(target_condition, c("CONTROL", "WARM", "LOSS")))
ggplot(bfi_stereo_df, aes(bfi_self_pmc, fit, group = itt_comp_gmc)) +
geom_smooth(method = "lm",
size = .7,
se = FALSE,
colour = "black",
aes(linetype = itt_comp_gmc)) +
theme_minimal(base_size = 13) +
theme(legend.key.size = unit(1, "cm")) +
facet_wrap(~target_condition,
labeller = labeller(target_condition = target_labels)) +
scale_linetype_manual("Threat composite",
breaks = c("-1.07", "0", "1.07"),
labels = c("Low",
"Average",
"High"),
values = c("solid",
"dashed",
"dotted"))+
labs(title = "Residual projection by target-level threat and target condition",
subtitle = "Using the BFI; After accounting for stereotyping",
x = "BFI responses for self",
y = "BFI responses for target")
# checking normality of conditional residuals
qqnorm(residuals(bfi_stereo), main="Q-Q plot for conditional residuals")
# checking the normality of the random effects
qqnorm(ranef(bfi_stereo)$sub_id$bfi_self_pmc,
main="Q-Q plot for the self random effect")
qqnorm(ranef(bfi_stereo)$sub_id$bfi_stereo_pmc,
main="Q-Q plot for the stereotyping random effect")
# Checking residuals for intercept
qqnorm(ranef(bfi_stereo)$sub_id$`(Intercept)`,
main="Q-Q plot for the random intercept")
plot_model(bfi_stereo, type='diag')
## [[1]]
##
## [[2]]
## [[2]]$sub_id
##
##
## [[3]]
##
## [[4]]
Definitely a tail, but only a few points, so most likely robust; stereo is the worst, may need to transform it
data_bfi_prolific <- clean_data_bfi %>%
filter(data_site != "uo") %>%
select(sub_id, bfi_number, bfi_targ_pmc, bfi_self_pmc, itt_comp_gmc,
target_condition, bfi_targ, bfi_self, bfi_stereo, bfi_stereo_pmc) %>%
unique() %>%
na.omit()
bfi_nostereo_comp_pro <- lmer(bfi_targ_pmc ~ bfi_self_pmc*itt_comp_gmc +
(bfi_self_pmc | sub_id), data = data_bfi_prolific)
summary(bfi_nostereo_comp_pro)
## Linear mixed model fit by REML ['lmerMod']
## Formula: bfi_targ_pmc ~ bfi_self_pmc * itt_comp_gmc + (bfi_self_pmc |
## sub_id)
## Data: data_bfi_prolific
##
## REML criterion at convergence: 22328.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.7520 -0.6118 -0.0211 0.6556 3.5462
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## sub_id (Intercept) 0.15466 0.3933
## bfi_self_pmc 0.05776 0.2403 0.65
## Residual 0.94523 0.9722
## Number of obs: 7695, groups: sub_id, 405
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) 0.001278 0.022604 0.057
## bfi_self_pmc 0.005070 0.014922 0.340
## itt_comp_gmc -0.290318 0.021185 -13.704
## bfi_self_pmc:itt_comp_gmc -0.137288 0.013909 -9.870
##
## Correlation of Fixed Effects:
## (Intr) bf_sl_ itt_c_
## bfi_slf_pmc 0.452
## itt_cmp_gmc -0.015 -0.005
## bf_slf_p:__ -0.005 -0.029 0.443
tab_model(bfi_nostereo_comp_pro)
| bfi_targ_pmc | |||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 0.00 | -0.04 – 0.05 | 0.955 |
| bfi self pmc | 0.01 | -0.02 – 0.03 | 0.734 |
| itt comp gmc | -0.29 | -0.33 – -0.25 | <0.001 |
|
bfi self pmc * itt comp gmc |
-0.14 | -0.16 – -0.11 | <0.001 |
| Random Effects | |||
| σ2 | 0.95 | ||
| τ00 sub_id | 0.15 | ||
| τ11 sub_id.bfi_self_pmc | 0.06 | ||
| ρ01 sub_id | 0.65 | ||
| ICC | 0.21 | ||
| N sub_id | 405 | ||
| Observations | 7695 | ||
| Marginal R2 / Conditional R2 | 0.104 / 0.296 | ||
Did not change
bfi_nostereo_comp_pro <- emtrends(bfi_nostereo_comp_pro , ~ itt_comp_gmc,
var ="bfi_self_pmc",
at = c(threat_levels))
bfi_nostereo_comp_pro
## itt_comp_gmc bfi_self_pmc.trend SE df asymp.LCL asymp.UCL
## -1.07 0.15197 0.0214 Inf 0.1101 0.1939
## 0.00 0.00507 0.0149 Inf -0.0242 0.0343
## 1.07 -0.14183 0.0208 Inf -0.1825 -0.1011
##
## Degrees-of-freedom method: asymptotic
## Confidence level used: 0.95
Did not change
bfi_nostereo_pro <- lmer(bfi_targ_pmc ~ bfi_self_pmc*itt_comp_gmc*target_condition +
(bfi_self_pmc | sub_id), data = data_bfi_prolific)
summary(bfi_nostereo_pro)
## Linear mixed model fit by REML ['lmerMod']
## Formula: bfi_targ_pmc ~ bfi_self_pmc * itt_comp_gmc * target_condition +
## (bfi_self_pmc | sub_id)
## Data: data_bfi_prolific
##
## REML criterion at convergence: 22269.6
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.7284 -0.6144 -0.0055 0.6469 3.5731
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## sub_id (Intercept) 0.11573 0.3402
## bfi_self_pmc 0.05207 0.2282 0.60
## Residual 0.94543 0.9723
## Number of obs: 7695, groups: sub_id, 405
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) 0.30971 0.05485 5.647
## bfi_self_pmc 0.16328 0.03907 4.180
## itt_comp_gmc -0.08358 0.04373 -1.911
## target_conditionLOSS -0.59811 0.07521 -7.953
## target_conditionWARM -0.22388 0.06753 -3.315
## bfi_self_pmc:itt_comp_gmc -0.02834 0.03106 -0.912
## bfi_self_pmc:target_conditionLOSS -0.27052 0.05389 -5.020
## bfi_self_pmc:target_conditionWARM -0.13306 0.04819 -2.761
## itt_comp_gmc:target_conditionLOSS -0.15637 0.06812 -2.296
## itt_comp_gmc:target_conditionWARM -0.11660 0.06126 -1.903
## bfi_self_pmc:itt_comp_gmc:target_conditionLOSS -0.07409 0.04836 -1.532
## bfi_self_pmc:itt_comp_gmc:target_conditionWARM -0.09378 0.04363 -2.150
##
## Correlation of Fixed Effects:
## (Intr) bf_sl_ itt_c_ t_LOSS t_WARM bf__:__ b__:_L b__:_W i__:_L
## bfi_slf_pmc 0.410
## itt_cmp_gmc 0.779 0.320
## trgt_cnLOSS -0.729 -0.299 -0.568
## trgt_cnWARM -0.812 -0.333 -0.633 0.592
## bf_slf_p:__ 0.321 0.780 0.398 -0.234 -0.260
## bf_s_:_LOSS -0.297 -0.725 -0.232 0.395 0.241 -0.566
## bf_s_:_WARM -0.332 -0.811 -0.259 0.242 0.412 -0.633 0.588
## itt__:_LOSS -0.500 -0.205 -0.642 -0.003 0.406 -0.255 0.012 0.166
## itt__:_WARM -0.556 -0.228 -0.714 0.406 0.262 -0.284 0.166 0.102 0.458
## b__:__:_LOS -0.206 -0.501 -0.255 0.012 0.167 -0.642 -0.014 0.406 0.382
## b__:__:_WAR -0.228 -0.556 -0.283 0.167 0.102 -0.712 0.403 0.250 0.182
## i__:_W b__:__:_L
## bfi_slf_pmc
## itt_cmp_gmc
## trgt_cnLOSS
## trgt_cnWARM
## bf_slf_p:__
## bf_s_:_LOSS
## bf_s_:_WARM
## itt__:_LOSS
## itt__:_WARM
## b__:__:_LOS 0.182
## b__:__:_WAR 0.402 0.457
tab_model(bfi_nostereo_pro)
| bfi_targ_pmc | |||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 0.31 | 0.20 – 0.42 | <0.001 |
| bfi self pmc | 0.16 | 0.09 – 0.24 | <0.001 |
| itt comp gmc | -0.08 | -0.17 – 0.00 | 0.056 |
| target condition [LOSS] | -0.60 | -0.75 – -0.45 | <0.001 |
| target condition [WARM] | -0.22 | -0.36 – -0.09 | 0.001 |
|
bfi self pmc * itt comp gmc |
-0.03 | -0.09 – 0.03 | 0.362 |
|
bfi self pmc * target condition [LOSS] |
-0.27 | -0.38 – -0.16 | <0.001 |
|
bfi self pmc * target condition [WARM] |
-0.13 | -0.23 – -0.04 | 0.006 |
|
itt comp gmc * target condition [LOSS] |
-0.16 | -0.29 – -0.02 | 0.022 |
|
itt comp gmc * target condition [WARM] |
-0.12 | -0.24 – 0.00 | 0.057 |
|
(bfi self pmc * itt comp gmc) * target condition [LOSS] |
-0.07 | -0.17 – 0.02 | 0.126 |
|
(bfi self pmc * itt comp gmc) * target condition [WARM] |
-0.09 | -0.18 – -0.01 | 0.032 |
| Random Effects | |||
| σ2 | 0.95 | ||
| τ00 sub_id | 0.12 | ||
| τ11 sub_id.bfi_self_pmc | 0.05 | ||
| ρ01 sub_id | 0.60 | ||
| ICC | 0.18 | ||
| N sub_id | 405 | ||
| Observations | 7695 | ||
| Marginal R2 / Conditional R2 | 0.142 / 0.297 | ||
Did not change
bfi_nostereo_targ_pro <- emtrends(bfi_nostereo_pro, ~ itt_comp_gmc*target_condition,
var ="bfi_self_pmc",
at = c(targ_levels, threat_levels))
bfi_nostereo_targ_pro
## itt_comp_gmc target_condition bfi_self_pmc.trend SE df asymp.LCL
## -1.07 CONTROL 0.19361 0.0246 Inf 0.145418
## 0.00 CONTROL 0.16328 0.0391 Inf 0.086714
## 1.07 CONTROL 0.13296 0.0682 Inf -0.000797
## -1.07 LOSS 0.00237 0.0711 Inf -0.136997
## 0.00 LOSS -0.10723 0.0371 Inf -0.179981
## 1.07 LOSS -0.21684 0.0291 Inf -0.273819
## -1.07 WARM 0.16089 0.0526 Inf 0.057729
## 0.00 WARM 0.03022 0.0282 Inf -0.025077
## 1.07 WARM -0.10044 0.0312 Inf -0.161506
## asymp.UCL
## 0.2418
## 0.2398
## 0.2667
## 0.1417
## -0.0345
## -0.1599
## 0.2640
## 0.0855
## -0.0394
##
## Degrees-of-freedom method: asymptotic
## Confidence level used: 0.95
Did not change
bfi_stereo_comp_pro <- lmer(bfi_targ_pmc ~ bfi_self_pmc*itt_comp_gmc*bfi_stereo_pmc +
(bfi_self_pmc + bfi_stereo_pmc | sub_id), data = data_bfi_prolific)
summary(bfi_stereo_comp_pro)
## Linear mixed model fit by REML ['lmerMod']
## Formula: bfi_targ_pmc ~ bfi_self_pmc * itt_comp_gmc * bfi_stereo_pmc +
## (bfi_self_pmc + bfi_stereo_pmc | sub_id)
## Data: data_bfi_prolific
##
## REML criterion at convergence: 20454.9
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.2655 -0.5014 -0.0403 0.6150 4.2109
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## sub_id (Intercept) 0.12934 0.3596
## bfi_self_pmc 0.03863 0.1965 0.47
## bfi_stereo_pmc 0.06842 0.2616 -0.69 -0.08
## Residual 0.70147 0.8375
## Number of obs: 7695, groups: sub_id, 405
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) 0.011888 0.020777 0.572
## bfi_self_pmc 0.070038 0.012904 5.428
## itt_comp_gmc -0.251778 0.019494 -12.916
## bfi_stereo_pmc 0.228417 0.016169 14.127
## bfi_self_pmc:itt_comp_gmc -0.076118 0.012059 -6.312
## bfi_self_pmc:bfi_stereo_pmc -0.021265 0.006406 -3.320
## itt_comp_gmc:bfi_stereo_pmc 0.189356 0.015116 12.527
## bfi_self_pmc:itt_comp_gmc:bfi_stereo_pmc -0.002961 0.005821 -0.509
##
## Correlation of Fixed Effects:
## (Intr) bf_sl_ itt_c_ bf_st_ bf_slf_pmc:t__ bf_slf_pmc:b__ i__:__
## bfi_slf_pmc 0.300
## itt_cmp_gmc -0.016 0.006
## bfi_str_pmc -0.481 0.049 0.033
## bf_slf_pmc:t__ 0.006 -0.042 0.292 -0.006
## bf_slf_pmc:b__ 0.142 -0.084 -0.013 0.073 0.050
## itt_cmp_:__ 0.033 -0.007 -0.480 -0.077 0.052 -0.001
## bf_s_:__:__ -0.013 0.050 0.148 -0.004 -0.080 -0.196 0.057
tab_model(bfi_stereo_comp_pro)
| bfi_targ_pmc | |||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 0.01 | -0.03 – 0.05 | 0.567 |
| bfi self pmc | 0.07 | 0.04 – 0.10 | <0.001 |
| itt comp gmc | -0.25 | -0.29 – -0.21 | <0.001 |
| bfi stereo pmc | 0.23 | 0.20 – 0.26 | <0.001 |
|
bfi self pmc * itt comp gmc |
-0.08 | -0.10 – -0.05 | <0.001 |
|
bfi self pmc * bfi stereo pmc |
-0.02 | -0.03 – -0.01 | 0.001 |
|
itt comp gmc * bfi stereo pmc |
0.19 | 0.16 – 0.22 | <0.001 |
|
(bfi self pmc * itt comp gmc) * bfi stereo pmc |
-0.00 | -0.01 – 0.01 | 0.611 |
| Random Effects | |||
| σ2 | 0.70 | ||
| τ00 sub_id | 0.13 | ||
| τ11 sub_id.bfi_self_pmc | 0.04 | ||
| τ11 sub_id.bfi_stereo_pmc | 0.07 | ||
| ρ01 | 0.47 | ||
| -0.69 | |||
| ICC | 0.31 | ||
| N sub_id | 405 | ||
| Observations | 7695 | ||
| Marginal R2 / Conditional R2 | 0.221 / 0.463 | ||
Did not change
bfi_stereo_comp_pro <- emtrends(bfi_stereo_comp_pro, ~ itt_comp_gmc,
var ="bfi_self_pmc",
at = c(threat_levels))
bfi_stereo_comp_pro
## itt_comp_gmc bfi_self_pmc.trend SE df asymp.LCL asymp.UCL
## -1.07 0.1520 0.0187 Inf 0.1154 0.1886
## 0.00 0.0707 0.0129 Inf 0.0454 0.0960
## 1.07 -0.0107 0.0179 Inf -0.0457 0.0244
##
## Degrees-of-freedom method: asymptotic
## Confidence level used: 0.95
Did not change
bfi_stereo_pro <- lmer(bfi_targ_pmc ~ bfi_self_pmc*itt_comp_gmc*target_condition*bfi_stereo_pmc +
(bfi_self_pmc + bfi_stereo_pmc | sub_id), data = data_bfi_prolific)
summary(bfi_stereo_pro)
## Linear mixed model fit by REML ['lmerMod']
## Formula: bfi_targ_pmc ~ bfi_self_pmc * itt_comp_gmc * target_condition *
## bfi_stereo_pmc + (bfi_self_pmc + bfi_stereo_pmc | sub_id)
## Data: data_bfi_prolific
##
## REML criterion at convergence: 20393.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.2581 -0.5083 -0.0246 0.6100 4.1923
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## sub_id (Intercept) 0.09077 0.3013
## bfi_self_pmc 0.03690 0.1921 0.44
## bfi_stereo_pmc 0.05134 0.2266 -0.57 0.02
## Residual 0.70135 0.8375
## Number of obs: 7695, groups: sub_id, 405
##
## Fixed effects:
## Estimate
## (Intercept) 0.280067
## bfi_self_pmc 0.158890
## itt_comp_gmc -0.094328
## target_conditionLOSS -0.615507
## target_conditionWARM -0.189430
## bfi_stereo_pmc 0.016193
## bfi_self_pmc:itt_comp_gmc -0.007248
## bfi_self_pmc:target_conditionLOSS -0.141784
## bfi_self_pmc:target_conditionWARM -0.058419
## itt_comp_gmc:target_conditionLOSS -0.040330
## itt_comp_gmc:target_conditionWARM -0.049353
## bfi_self_pmc:bfi_stereo_pmc -0.033151
## itt_comp_gmc:bfi_stereo_pmc 0.067417
## target_conditionLOSS:bfi_stereo_pmc 0.445262
## target_conditionWARM:bfi_stereo_pmc 0.200130
## bfi_self_pmc:itt_comp_gmc:target_conditionLOSS -0.061065
## bfi_self_pmc:itt_comp_gmc:target_conditionWARM -0.073954
## bfi_self_pmc:itt_comp_gmc:bfi_stereo_pmc -0.018925
## bfi_self_pmc:target_conditionLOSS:bfi_stereo_pmc -0.018850
## bfi_self_pmc:target_conditionWARM:bfi_stereo_pmc 0.012389
## itt_comp_gmc:target_conditionLOSS:bfi_stereo_pmc 0.021707
## itt_comp_gmc:target_conditionWARM:bfi_stereo_pmc 0.048238
## bfi_self_pmc:itt_comp_gmc:target_conditionLOSS:bfi_stereo_pmc 0.044810
## bfi_self_pmc:itt_comp_gmc:target_conditionWARM:bfi_stereo_pmc 0.021115
## Std. Error
## (Intercept) 0.049133
## bfi_self_pmc 0.034002
## itt_comp_gmc 0.039235
## target_conditionLOSS 0.067567
## target_conditionWARM 0.060540
## bfi_stereo_pmc 0.038360
## bfi_self_pmc:itt_comp_gmc 0.027189
## bfi_self_pmc:target_conditionLOSS 0.047482
## bfi_self_pmc:target_conditionWARM 0.042107
## itt_comp_gmc:target_conditionLOSS 0.061264
## itt_comp_gmc:target_conditionWARM 0.055060
## bfi_self_pmc:bfi_stereo_pmc 0.015449
## itt_comp_gmc:bfi_stereo_pmc 0.031029
## target_conditionLOSS:bfi_stereo_pmc 0.055177
## target_conditionWARM:bfi_stereo_pmc 0.048172
## bfi_self_pmc:itt_comp_gmc:target_conditionLOSS 0.042758
## bfi_self_pmc:itt_comp_gmc:target_conditionWARM 0.038278
## bfi_self_pmc:itt_comp_gmc:bfi_stereo_pmc 0.012571
## bfi_self_pmc:target_conditionLOSS:bfi_stereo_pmc 0.023706
## bfi_self_pmc:target_conditionWARM:bfi_stereo_pmc 0.020320
## itt_comp_gmc:target_conditionLOSS:bfi_stereo_pmc 0.049974
## itt_comp_gmc:target_conditionWARM:bfi_stereo_pmc 0.043889
## bfi_self_pmc:itt_comp_gmc:target_conditionLOSS:bfi_stereo_pmc 0.020682
## bfi_self_pmc:itt_comp_gmc:target_conditionWARM:bfi_stereo_pmc 0.018432
## t value
## (Intercept) 5.700
## bfi_self_pmc 4.673
## itt_comp_gmc -2.404
## target_conditionLOSS -9.110
## target_conditionWARM -3.129
## bfi_stereo_pmc 0.422
## bfi_self_pmc:itt_comp_gmc -0.267
## bfi_self_pmc:target_conditionLOSS -2.986
## bfi_self_pmc:target_conditionWARM -1.387
## itt_comp_gmc:target_conditionLOSS -0.658
## itt_comp_gmc:target_conditionWARM -0.896
## bfi_self_pmc:bfi_stereo_pmc -2.146
## itt_comp_gmc:bfi_stereo_pmc 2.173
## target_conditionLOSS:bfi_stereo_pmc 8.070
## target_conditionWARM:bfi_stereo_pmc 4.154
## bfi_self_pmc:itt_comp_gmc:target_conditionLOSS -1.428
## bfi_self_pmc:itt_comp_gmc:target_conditionWARM -1.932
## bfi_self_pmc:itt_comp_gmc:bfi_stereo_pmc -1.505
## bfi_self_pmc:target_conditionLOSS:bfi_stereo_pmc -0.795
## bfi_self_pmc:target_conditionWARM:bfi_stereo_pmc 0.610
## itt_comp_gmc:target_conditionLOSS:bfi_stereo_pmc 0.434
## itt_comp_gmc:target_conditionWARM:bfi_stereo_pmc 1.099
## bfi_self_pmc:itt_comp_gmc:target_conditionLOSS:bfi_stereo_pmc 2.167
## bfi_self_pmc:itt_comp_gmc:target_conditionWARM:bfi_stereo_pmc 1.146
tab_model(bfi_stereo_pro)
| bfi_targ_pmc | |||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 0.28 | 0.18 – 0.38 | <0.001 |
| bfi self pmc | 0.16 | 0.09 – 0.23 | <0.001 |
| itt comp gmc | -0.09 | -0.17 – -0.02 | 0.016 |
| target condition [LOSS] | -0.62 | -0.75 – -0.48 | <0.001 |
| target condition [WARM] | -0.19 | -0.31 – -0.07 | 0.002 |
| bfi stereo pmc | 0.02 | -0.06 – 0.09 | 0.673 |
|
bfi self pmc * itt comp gmc |
-0.01 | -0.06 – 0.05 | 0.790 |
|
bfi self pmc * target condition [LOSS] |
-0.14 | -0.23 – -0.05 | 0.003 |
|
bfi self pmc * target condition [WARM] |
-0.06 | -0.14 – 0.02 | 0.165 |
|
itt comp gmc * target condition [LOSS] |
-0.04 | -0.16 – 0.08 | 0.510 |
|
itt comp gmc * target condition [WARM] |
-0.05 | -0.16 – 0.06 | 0.370 |
|
bfi self pmc * bfi stereo pmc |
-0.03 | -0.06 – -0.00 | 0.032 |
|
itt comp gmc * bfi stereo pmc |
0.07 | 0.01 – 0.13 | 0.030 |
|
target condition [LOSS] * bfi stereo pmc |
0.45 | 0.34 – 0.55 | <0.001 |
|
target condition [WARM] * bfi stereo pmc |
0.20 | 0.11 – 0.29 | <0.001 |
|
(bfi self pmc * itt comp gmc) * target condition [LOSS] |
-0.06 | -0.14 – 0.02 | 0.153 |
|
(bfi self pmc * itt comp gmc) * target condition [WARM] |
-0.07 | -0.15 – 0.00 | 0.053 |
|
(bfi self pmc * itt comp gmc) * bfi stereo pmc |
-0.02 | -0.04 – 0.01 | 0.132 |
|
(bfi self pmc * target condition [LOSS]) * bfi stereo pmc |
-0.02 | -0.07 – 0.03 | 0.427 |
|
(bfi self pmc * target condition [WARM]) * bfi stereo pmc |
0.01 | -0.03 – 0.05 | 0.542 |
|
(itt comp gmc * target condition [LOSS]) * bfi stereo pmc |
0.02 | -0.08 – 0.12 | 0.664 |
|
(itt comp gmc * target condition [WARM]) * bfi stereo pmc |
0.05 | -0.04 – 0.13 | 0.272 |
|
(bfi self pmc * itt comp gmc * target condition [LOSS]) * bfi stereo pmc |
0.04 | 0.00 – 0.09 | 0.030 |
|
(bfi self pmc * itt comp gmc * target condition [WARM]) * bfi stereo pmc |
0.02 | -0.02 – 0.06 | 0.252 |
| Random Effects | |||
| σ2 | 0.70 | ||
| τ00 sub_id | 0.09 | ||
| τ11 sub_id.bfi_self_pmc | 0.04 | ||
| τ11 sub_id.bfi_stereo_pmc | 0.05 | ||
| ρ01 | 0.44 | ||
| -0.57 | |||
| ICC | 0.26 | ||
| N sub_id | 405 | ||
| Observations | 7695 | ||
| Marginal R2 / Conditional R2 | 0.277 / 0.462 | ||
The interaction of self, comp, and condition becomes marginal (.053) when we remove the UO participants
bfi_stereo_targ_pro <- emtrends(bfi_stereo_pro, ~ itt_comp_gmc*target_condition,
var ="bfi_self_pmc",
at = c(targ_levels, threat_levels))
bfi_stereo_targ_pro
## itt_comp_gmc target_condition bfi_self_pmc.trend SE df asymp.LCL
## -1.07 CONTROL 0.1670 0.0218 Inf 0.1243
## 0.00 CONTROL 0.1599 0.0340 Inf 0.0932
## 1.07 CONTROL 0.1528 0.0595 Inf 0.0362
## -1.07 LOSS 0.0926 0.0638 Inf -0.0324
## 0.00 LOSS 0.0187 0.0333 Inf -0.0465
## 1.07 LOSS -0.0552 0.0255 Inf -0.1052
## -1.07 WARM 0.1881 0.0464 Inf 0.0971
## 0.00 WARM 0.1011 0.0249 Inf 0.0523
## 1.07 WARM 0.0141 0.0274 Inf -0.0396
## asymp.UCL
## 0.20981
## 0.22660
## 0.26931
## 0.21765
## 0.08386
## -0.00534
## 0.27900
## 0.14987
## 0.06791
##
## Degrees-of-freedom method: asymptotic
## Confidence level used: 0.95
However, simple slopes show that residual counter-projection still persists in the same circumstances, which is the most important result.
cor_bfi <- data_bfi %>%
select(bfi_self_pmc, bfi_stereo_pmc, bfi_targ_pmc, itt_comp_gmc) %>%
unique() %>%
rename("BFI: Self" = bfi_self_pmc,
"BFI: Stereo" = bfi_stereo_pmc,
"BFI: Target" = bfi_targ_pmc,
"Threat Composite" = itt_comp_gmc)
correlations_preds <- cor(cor_bfi)
corrplot(correlations_preds,
is.corr = TRUE,
#method = "number",
method = 'color',
tl.cex = .85,
tl.col = 'black',
addgrid.col = 'white',
addCoef.col = 'grey50')